Alagappan
Work

Object Detection Using Machine Learning

Real-time browser-based object detection using live camera input and client-side ML inference — no cloud API, no server round-trips.

Object Detection Using Machine Learning

Built a real-time object detection system that runs entirely in the browser. Uses live camera input via WebRTC and runs ML inference on-device with ml5.js — no frames are ever sent to a cloud API.

Most object detection demos send every camera frame to a cloud API for processing. That introduces latency, costs money at scale, and raises privacy concerns. This system eliminates the round-trip entirely by running the model locally in the browser.

  1. WebRTC captures live video from the device camera
  2. ml5.js runs the pre-trained COCO-SSD model directly in the browser via TensorFlow.js
  3. Detected objects are overlaid on the video feed in real time
  • Zero server dependency — all inference happens on the client
  • Reduced latency — no network round-trip for each frame
  • Privacy-preserving — camera data never leaves the device
  • JavaScript
  • WebRTC (camera input)
  • ml5.js (client-side ML)
  • TensorFlow.js (underlying inference engine)
Software DeveloperChennai      IST